FBI 发布 FLASH 警报:开源 LLM 智能体渗透测试框架 ARTEX 被攻击者武器化用于自动化入侵
AI 导读
FBI 于 2026 年 11 月 13 日发布 FLASH 通报,警告至少自 2026 年 8 月起,多种恶意网络行为者武器化开源 LLM 智能体渗透测试框架 ARTEX,在全球对金融、政府、科技等多个行业实施自动化入侵。通报称 ARTEX 大幅缩短串联攻击技术的时间,部分入侵从初始目标锁定到获得特权访问不到三小时,技术能力有限的攻击者也能借此同时开展多目标行动;案例包括针对韩国金融机构的攻击窃取约 67,000 人个人信息,以及波及超过 2,250 个下游租户的 ConnectWise Cloud Backup 供应链入侵。原开发者在 2026 年 10 月删除 GitHub 仓库后,该框架仍经社区分支、存档副本和商业版 ARTEX PRO 扩散,截至 2026 年 11 月初,研究人员发现 1,600 个公开暴露的 ARTEX 控制台实例。FBI 建议运营互联网暴露应用、自助门户、云基础设施和合作伙伴系统的组织落实通报中的缓解措施。
推荐理由
FBI 通报了攻击者用开源 LLM 智能体框架 ARTEX 实施入侵的真实案例与 IOC,运营互联网暴露系统的团队可对照其缓解措施自查。
正文 · 原文
https://www.ic3.gov/CSA/2026/261113.pdf
Threat actors are weaponizing ARTEX, an open-source, large language model (LLM)-driven agentic platform to automate multiple phases of cyber intrusions at machine speed. Since at least August 2026, a variety of malicious cyber actors have used ARTEX to conduct campaigns targeting organizations globally across multiple sectors, including financial services, government, and technology.
ARTEX significantly reduces the time required to chain attack techniques and enables threat actors with minimal technical expertise to conduct complex, multi-target operations simultaneously.
Today, the FBI released a FLASH highlighting the tactics, techniques, and procedures and indicators of compromise associated with the ARTEX framework. Organizations should follow the mitigation steps outlined in the FLASH to improve their security posture in response to ARTEX and similar agentic SI frameworks: https://www.ic3.gov/CSA/2026/261113.pdf在 X 查看被引用的帖子